© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 69242
    Prev
    Next
    INDEX
    Explanations

    phrases indicating location or outcome

    np_acts-logits-general · gemini-2.5-flash-lite

    discussing abstract concepts or observable phenomena

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cuadrados
    0.52
     システム
    0.50
    漑
    0.50
     systèmes
    0.47
     نړۍ
    0.47
     bici
    0.47
     Catawiki
    0.47
     পৃথিব
    0.47
     調
    0.46
    があります
    0.46
    POSITIVE LOGITS
    eneg
    0.48
    ganggu
    0.47
    Suff
    0.45
    ндар
    0.44
    immä
    0.43
    ξύ
    0.42
    odrome
    0.41
     asphy
    0.41
    onitrile
    0.41
     brilliance
    0.41
    Activations Density 0.001%

    No Known Activations